Knowledge & Memory

A lightweight, Git-backed permanent memory for AI agents.

Self-curating agent memory kept honest by survival-based selection over measured outcomes.

Portable agent memory anchored on Solana. Local SQLite + vector recall, open export.

Model Context Protocol server for AgentRAM. Persistent memory for AI agents.

Persistent memory for AI tools. Local-first knowledge graph with hybrid search.

Persistent AI memory using orbital mechanics. 100% local, zero API keys, MCP-native.

Ebbinghaus-based persistent memory for Claude. Memories decay with time, strengthen on recall.

MCP server for Ordali memory: SQLite-backed project memory and governance traces.

Local-first AI memory cartridge with persistent MCP memory for Claude via SQLite FTS5.

Session memory for AI coding agents: records decisions and dead ends, flags what went stale.

Code knowledge graph over MCP: token-budgeted context for AI coding agents.

Persistent memory for Claude via weighted, interconnected knowledge nodes.

Role-aware Agent memory with cross-session recall, durable writes, and multi-Agent project scope.

Cognitive memory for AI coding assistants — persistent memory across sessions

Intelligent code knowledge graph for AI coding agents — 71% cheaper, 72% faster

Secure, fragment-based long-term memory for MCP-compatible AI agents.

Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.

Local-first persistent memory for AI coding agents.

Cross-machine, file-first memory for Claude Code: markdown + SQLite FTS5, synced with git

Lightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.